Noometry

Model comparison

Claude Opus 4.5 vs Kimi K2.5

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 47.8 on the Noometry Index. Kimi K2.5 costs 11× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 44 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #39 Confirmed

Kimi K2.5 Moonshot AI

47.8

Rank #50 Confirmed

Summary

  • They share 44 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and Kimi K2.5 in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.5 leads 47.2 to 34.0.
  • The biggest single-benchmark swing is ARC-AGI-2: 37.6% for Claude Opus 4.5 and 11.8% for Kimi K2.5.
  • Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Kimi K2.5 accepts more context: 262K tokens versus 200K.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5Kimi K2.5
ProviderAnthropicMoonshot AI
Noometry Index50.547.8
Released2025-11-012026-01-27
WeightsProprietaryOpen
Context window200K262K
Max output64K262K
Input $ / M tokens$5$0.45
Output $ / M tokens$25$2.25
Results tracked6951

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 55.4 (#21), Kimi K2.5: 48.7 (#48)

BenchmarkClaude Opus 4.5Kimi K2.5
SWE-bench Verified76.7%73.8%
SWE-bench Verified (bash only)76.8%70.8%
LMArena WebDev14931436
SWE-bench Multilingual70.7%67.3%
WeirdML63.7%45.6%
LMArena Coding15041474
ALE-Bench1,025821.65
SciCode—49%
GSO26.5%—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.2 (#11), Kimi K2.5: 34.0 (#44)

BenchmarkClaude Opus 4.5Kimi K2.5
Terminal-Bench63.1%43.2%
OSWorld66.3%63.3%
Vending-Bench 24,9671,198
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
BALROG43.5%—
LMArena Search1180—
METR Time Horizons75%—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.5 (#43), Kimi K2.5: 31.2 (#74)

BenchmarkClaude Opus 4.5Kimi K2.5
ARC-AGI-237.6%11.8%
SimpleBench62%46.8%
Kagi LLM Benchmark80.2%78.5%
NYT Connections (extended)52.5%69.9%
ARC-AGI-180%65.3%
Chess Puzzles12%12%
EnigmaEval11.9%3.4%
LMArena Hard Prompts14761454
Epoch Capabilities Index150.1148.05
CritPt—3.1%
Thematic Generalization—69.4%
EBR-Bench14.3%—
Mystery Game Puzzles22%—
DTBench89.9%—
LMCA44.5%—
ForecastBench60.7—

Math Kimi K2.5 leads

Claude Opus 4.5: 38.5 (#85), Kimi K2.5: 50.3 (#46)

BenchmarkClaude Opus 4.5Kimi K2.5
OTIS Mock AIME 2024-202586.1%92.2%
LMArena Math14631470
FrontierMath (Feb 2025 set)20.7%27.9%
FrontierMath Tier 4 (v1)4.2%4.2%
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
MathArena Final-Answer Competitions—62.3%
ProofBench36%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.4 (#38), Kimi K2.5: 53.6 (#52)

BenchmarkClaude Opus 4.5Kimi K2.5
GPQA Diamond86%87.6%
Humanity's Last Exam25.2%24.4%
SimpleQA Verified45.7%34.3%
Vectara Hallucination Rate10.9%14.2%
LMArena Expert14881466

Multimodal Kimi K2.5 leads

Claude Opus 4.5: 31.1 (#99), Kimi K2.5: 40.4 (#37)

BenchmarkClaude Opus 4.5Kimi K2.5
LMArena Document14621430
LMArena Vision—1269
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—

Multilingual Too close to call

Claude Opus 4.5: 54.5 (#45), Kimi K2.5: 54.1 (#50)

BenchmarkClaude Opus 4.5Kimi K2.5
LMArena Non-English14381433
LMArena Chinese14701495
LMArena French14711454
LMArena German14491441
LMArena Japanese14151422
LMArena Korean14241412
LMArena Russian14481436
LMArena Spanish14551450

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.7 (#20), Kimi K2.5: 75.5 (#60)

BenchmarkClaude Opus 4.5Kimi K2.5
LMArena Instruction Following14781431

Long Context Kimi K2.5 leads

Claude Opus 4.5: 46.4 (#21), Kimi K2.5: 52.1 (#7)

BenchmarkClaude Opus 4.5Kimi K2.5
CL-bench21.1%19.3%
LMArena Longer Query14801445
Fiction.LiveBench—86.1%
CL-bench Life—13.2%

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.2 (#28), Kimi K2.5: 65.3 (#51)

BenchmarkClaude Opus 4.5Kimi K2.5
LMArena Text14511445
LMArena Creative Writing14451423
EQ-Bench Creative Writing16871579
LMArena Multi-Turn14661444

Frequently asked questions

Is Claude Opus 4.5 better than Kimi K2.5?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 47.8 on the Noometry Index. Kimi K2.5 costs 11× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 or Kimi K2.5?

Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Kimi K2.5 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 48.7 in the Noometry coding category.

Which has the bigger context window?

Kimi K2.5 does, with 262K tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Kimi K2.5 share?

44 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper